gemini: minimal thinking on correlation, token accounting per call

A day of replay runs (server-26#170) spent ~$5 of Gemini on ~7 two-hour
windows (~$0.70 per 290 calls) — several dollars a day per live deployment
for correlation alone — and nothing could say where it went (#45). Gemini
3.x thinks by default and bills it as output; the deprecated
google-generativeai SDK these calls used cannot set a thinking level.

- app/internal/gemini.py: every Gemini call (correlation + transcript
  correction) goes through google-genai with JSON mode, an explicit
  thinking level, and logs in/out/thinking tokens. A model that rejects
  the level is retried without it once and remembered, so the tier is
  never lost to a config param. API failures still raise for ai_health.
- correlator: thinking_level "minimal" (a link/new/orphan choice).
  transcript correction: "low" until a replay shows minimal is safe.
- replay: runs record real Gemini token usage (metrics.gemini_usage),
  shown in the Replay tab.
- requirements: google-genai.

c2-core: 474 pass. Frontend typecheck not run (no Node on this box).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

drb-c2-core/app/internal/transcript_correction.py

@@ -43,7 +43,6 @@ another equally plausible word.
 """
 
 import asyncio
-import json
 import re
 from typing import Any, Optional
 
@@ -228,14 +227,11 @@ def build_context_block(context: dict, talkgroup_name: Optional[str]) -> str:
 
 
 def _sync_gemini(model_name: str, prompt: str) -> dict:
-    import google.generativeai as genai  # lazy import — only when needed
-
-    genai.configure(api_key=settings.gemini_api_key)
-    model = genai.GenerativeModel(
-        model_name,
-        generation_config={"response_mime_type": "application/json"},
-    )
-    return json.loads(model.generate_content(prompt).text)
+    from app.internal import gemini
+    # Correction rewrites text against vocabulary; keep a little reasoning
+    # ("low") rather than the correlator's "minimal" until a replay shows
+    # minimal doesn't hurt it.
+    return gemini.generate_json(model_name, prompt, purpose="correction", thinking_level="low")
 
 
 async def correct(